{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KTKWJYVUGNDJ55YMH26YNRZN6U","short_pith_number":"pith:KTKWJYVU","schema_version":"1.0","canonical_sha256":"54d564e2b433469ef70c3ebd86c72df518df321c57bd8777c72dfdd250d7ff94","source":{"kind":"arxiv","id":"2307.00783","version":1},"attestation_state":"computed","paper":{"title":"Monte Carlo Policy Gradient Method for Binary Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"math.OC","authors_text":"Cheng Chen, Ruichen Ao, Ruitao Chen, Tianyou Li, Zaiwen Wen","submitted_at":"2023-07-03T07:01:42Z","abstract_excerpt":"Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT. However, these problems are typically NP-hard due to the binary constraints. We develop a novel probabilistic model to sample the binary solution according to a parameterized policy distribution. Specifically, minimizing the KL divergence between the parameterized policy distribution and the Gibbs distributions of the function value leads to a stochastic optimization problem whose policy gradient can be derived explicitly similar to reinforcement learning. For"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.00783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-03T07:01:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c24a1affb239a505623882874abddfb56a0f1b28323bb5add61abe4909a7979e","abstract_canon_sha256":"eecdc0d9ced17cef321dd2a47bd9d10ab1b5d0de0c973425f3c322dee465ef72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:00.467149Z","signature_b64":"Frz113JhDxReLN22GqLZoVK1mu/SLCMuwHiyKVkTngyHS/Lq6yEjYYSsM2oS2zs1HIHkohNL8IN5vOL5X1afCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d564e2b433469ef70c3ebd86c72df518df321c57bd8777c72dfdd250d7ff94","last_reissued_at":"2026-07-05T06:27:00.466687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:00.466687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monte Carlo Policy Gradient Method for Binary Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"math.OC","authors_text":"Cheng Chen, Ruichen Ao, Ruitao Chen, Tianyou Li, Zaiwen Wen","submitted_at":"2023-07-03T07:01:42Z","abstract_excerpt":"Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT. However, these problems are typically NP-hard due to the binary constraints. We develop a novel probabilistic model to sample the binary solution according to a parameterized policy distribution. Specifically, minimizing the KL divergence between the parameterized policy distribution and the Gibbs distributions of the function value leads to a stochastic optimization problem whose policy gradient can be derived explicitly similar to reinforcement learning. For"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00783","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.00783/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.00783","created_at":"2026-07-05T06:27:00.466761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00783v1","created_at":"2026-07-05T06:27:00.466761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00783","created_at":"2026-07-05T06:27:00.466761+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTKWJYVUGNDJ","created_at":"2026-07-05T06:27:00.466761+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTKWJYVUGNDJ55YM","created_at":"2026-07-05T06:27:00.466761+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTKWJYVU","created_at":"2026-07-05T06:27:00.466761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16598","citing_title":"Variational Evolutionary Network for Statistical Physics Systems","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U","json":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U.json","graph_json":"https://pith.science/api/pith-number/KTKWJYVUGNDJ55YMH26YNRZN6U/graph.json","events_json":"https://pith.science/api/pith-number/KTKWJYVUGNDJ55YMH26YNRZN6U/events.json","paper":"https://pith.science/paper/KTKWJYVU"},"agent_actions":{"view_html":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U","download_json":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U.json","view_paper":"https://pith.science/paper/KTKWJYVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00783&json=true","fetch_graph":"https://pith.science/api/pith-number/KTKWJYVUGNDJ55YMH26YNRZN6U/graph.json","fetch_events":"https://pith.science/api/pith-number/KTKWJYVUGNDJ55YMH26YNRZN6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/action/storage_attestation","attest_author":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/action/author_attestation","sign_citation":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/action/citation_signature","submit_replication":"https://pith.science/pith/KTKWJYVUGNDJ55YMH26YNRZN6U/action/replication_record"}},"created_at":"2026-07-05T06:27:00.466761+00:00","updated_at":"2026-07-05T06:27:00.466761+00:00"}